commit f4d67ae33a7f942d2005245249231157d09f9837 Author: ModelHub XC Date: Fri Aug 7 18:03:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7f943cc --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +LLama-3.1-8b-Ultra-Max-Pro.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama-3.1-8b-Ultra-Max-Pro.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama-3.1-8b-Ultra-Max-Pro.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLama-3.1-8b-Ultra-Max-Pro.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLama-3.1-8b-Ultra-Max-Pro.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama-3.1-8b-Ultra-Max-Pro.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama-3.1-8b-Ultra-Max-Pro.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama-3.1-8b-Ultra-Max-Pro.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLama-3.1-8b-Ultra-Max-Pro.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama-3.1-8b-Ultra-Max-Pro.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama-3.1-8b-Ultra-Max-Pro.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama-3.1-8b-Ultra-Max-Pro.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLama-3.1-8b-Ultra-Max-Pro.IQ4_XS.gguf b/LLama-3.1-8b-Ultra-Max-Pro.IQ4_XS.gguf new file mode 100644 index 0000000..eba74fd --- /dev/null +++ b/LLama-3.1-8b-Ultra-Max-Pro.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13e564f5dbfedd15207406afd75fc196870e4dafa5bcd6ec10d28d3a6bbb9348 +size 4484365152 diff --git a/LLama-3.1-8b-Ultra-Max-Pro.Q2_K.gguf b/LLama-3.1-8b-Ultra-Max-Pro.Q2_K.gguf new file mode 100644 index 0000000..349f53c --- /dev/null +++ b/LLama-3.1-8b-Ultra-Max-Pro.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd037da214cdffe7d6b3ff659f2e79ff2a9da427c87a5891b5e5e7a9f84af1cf +size 3179133792 diff --git a/LLama-3.1-8b-Ultra-Max-Pro.Q3_K_L.gguf b/LLama-3.1-8b-Ultra-Max-Pro.Q3_K_L.gguf new file mode 100644 index 0000000..232140d --- /dev/null +++ b/LLama-3.1-8b-Ultra-Max-Pro.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f383d8ebc213b8e63eda3120b9b8b305444e768f5c05c6455338b2028fd74065 +size 4321958752 diff --git a/LLama-3.1-8b-Ultra-Max-Pro.Q3_K_M.gguf b/LLama-3.1-8b-Ultra-Max-Pro.Q3_K_M.gguf new file mode 100644 index 0000000..10e8ea6 --- /dev/null +++ b/LLama-3.1-8b-Ultra-Max-Pro.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3499d43680a57b86fae3c28d79b13f671dae5c327d11fc11a35cbe4f8ac9e16 +size 4018920288 diff --git a/LLama-3.1-8b-Ultra-Max-Pro.Q3_K_S.gguf b/LLama-3.1-8b-Ultra-Max-Pro.Q3_K_S.gguf new file mode 100644 index 0000000..44a8b33 --- /dev/null +++ b/LLama-3.1-8b-Ultra-Max-Pro.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba0f354262d2f7d5f9bfa4ff0b116d50486206ce39821a2b9dca27907563bbb +size 3664501600 diff --git a/LLama-3.1-8b-Ultra-Max-Pro.Q4_K_M.gguf b/LLama-3.1-8b-Ultra-Max-Pro.Q4_K_M.gguf new file mode 100644 index 0000000..06934ce --- /dev/null +++ b/LLama-3.1-8b-Ultra-Max-Pro.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a09738efd802a29a92cc514f8c215e03cf3b740501458d987fae759002f7e5 +size 4920736608 diff --git a/LLama-3.1-8b-Ultra-Max-Pro.Q4_K_S.gguf b/LLama-3.1-8b-Ultra-Max-Pro.Q4_K_S.gguf new file mode 100644 index 0000000..44ad35f --- /dev/null +++ b/LLama-3.1-8b-Ultra-Max-Pro.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:646f865fe5ba6c1c28989c600b90e4b1416bf43fefffac8d0d0744548ef62108 +size 4692671328 diff --git a/LLama-3.1-8b-Ultra-Max-Pro.Q5_K_M.gguf b/LLama-3.1-8b-Ultra-Max-Pro.Q5_K_M.gguf new file mode 100644 index 0000000..46a448b --- /dev/null +++ b/LLama-3.1-8b-Ultra-Max-Pro.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:884ea4031ee5621b0658a8c0c333343976ef9e62787af3937810dad2dec3ab81 +size 5732989792 diff --git a/LLama-3.1-8b-Ultra-Max-Pro.Q5_K_S.gguf b/LLama-3.1-8b-Ultra-Max-Pro.Q5_K_S.gguf new file mode 100644 index 0000000..24d6dd5 --- /dev/null +++ b/LLama-3.1-8b-Ultra-Max-Pro.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1b7fa4deb504910d59540f463e28064d687428b5df705a9ab217c380b6b4316 +size 5599296352 diff --git a/LLama-3.1-8b-Ultra-Max-Pro.Q6_K.gguf b/LLama-3.1-8b-Ultra-Max-Pro.Q6_K.gguf new file mode 100644 index 0000000..f977416 --- /dev/null +++ b/LLama-3.1-8b-Ultra-Max-Pro.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07e87cd9297be0942c8d1a9832ea92c9907ac3ecea6be715200c1cc99c6145e7 +size 6596008800 diff --git a/LLama-3.1-8b-Ultra-Max-Pro.Q8_0.gguf b/LLama-3.1-8b-Ultra-Max-Pro.Q8_0.gguf new file mode 100644 index 0000000..fb80e45 --- /dev/null +++ b/LLama-3.1-8b-Ultra-Max-Pro.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:461bc7f711f83c71ceadfe3902819940df0a13225028c23ae3b8b03b5d3b6d7e +size 8540773216 diff --git a/LLama-3.1-8b-Ultra-Max-Pro.f16.gguf b/LLama-3.1-8b-Ultra-Max-Pro.f16.gguf new file mode 100644 index 0000000..debff23 --- /dev/null +++ b/LLama-3.1-8b-Ultra-Max-Pro.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1bb5666b26b15db32e4d2943375ed4181472c75861578ff966e8ea25ef9849f +size 16068893536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..42e9f71 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: bunnycore/LLama-3.1-8b-Ultra-Max-Pro +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/LLama-3.1-8b-Ultra-Max-Pro + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LLama-3.1-8b-Ultra-Max-Pro-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF/resolve/main/LLama-3.1-8b-Ultra-Max-Pro.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF/resolve/main/LLama-3.1-8b-Ultra-Max-Pro.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF/resolve/main/LLama-3.1-8b-Ultra-Max-Pro.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF/resolve/main/LLama-3.1-8b-Ultra-Max-Pro.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF/resolve/main/LLama-3.1-8b-Ultra-Max-Pro.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF/resolve/main/LLama-3.1-8b-Ultra-Max-Pro.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF/resolve/main/LLama-3.1-8b-Ultra-Max-Pro.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF/resolve/main/LLama-3.1-8b-Ultra-Max-Pro.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF/resolve/main/LLama-3.1-8b-Ultra-Max-Pro.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF/resolve/main/LLama-3.1-8b-Ultra-Max-Pro.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF/resolve/main/LLama-3.1-8b-Ultra-Max-Pro.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF/resolve/main/LLama-3.1-8b-Ultra-Max-Pro.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +